CoChat

De novo protein structure prediction by incremental inter-residue geometries prediction and model quality assessment using deep learning

Open access
Liu, Jun, He, Guang-Xing, Zhao, Kai-Long, Zhang, Gui-Jun · 2022 · bioRxiv (Cold Spring Harbor Laboratory)
PreprintCited by 6

The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.

Abstract

Motivation: The successful application of deep learning has promoted progress in protein model quality assessment. How to use model quality assessment to further improve the accuracy of protein structure prediction, especially not reliant on the existing templates, is helpful for unraveling the folding mechanism. Here, we investigate whether model quality assessment can be introduced into structure prediction to form a closed-loop feedback, and iteratively improve the accuracy of de novo protein structure prediction. Results: In this study, we propose a de novo protein structure prediction method called RocketX. In RocketX, a feedback mechanism is constructed through the geometric constraint prediction network GeomNet, the structural simulation module, and the model quality evaluation network EmaNet. In GeomNet, the co-evolutionary features extracted from MSA that search from the sequence databases are sent to an improved residual neural network to predict the inter-residue geometric constraints. The structure model is folded based on the predicted geometric constraints. In EmaNet, the 1D and 2D features are extracted from the folded model and sent to the deep residual neural network to estimate the inter-residue distance deviation and per-residue lDDT of the model, which will be fed back to GeomNet as dynamic features to correct the geometries prediction and progressively improve model accuracy. RocketX is tested on 483 benchmark proteins and 20 FM targets of CASP14. Experimental results show that the closed-loop feedback mechanism significantly contributes to the performance of RocketX, and the prediction accuracy of RocketX outperforms that of the state-of-the-art methods trRosetta (without templates) and RaptorX. In addition, the blind test results on CAMEO show that although no template is used, the prediction accuracy of RocketX on medium and hard targets is comparable to the advanced methods that integrate templates. Availability: The RocketX web server are freely available at http://zhanglab-bioinf.com/RocketX . Contact: zgj@zjut.edu.cn

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1101/2022.01.11.475831

Cites

18 of 18 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 55

  1. 10.1186/s12859-021-04034-6 · DOI · Paper page
  2. Alapati,R. and Bhattacharya, D. (2018) clustQ: Efficient protein decoy clustering using superposition-free weighted internal distance comparisons. In Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, 307–314. · DOI
  3. 10.1126/science.abj8754 · doi:10.1126/science.abj8754 · Paper page
  4. 2021, GraphQA: protein model quality assessment using graph convolutional networks, Bioinformatics, 37, 360, 10.1093/bioinformatics/btaa714 · DOI · Paper page
  5. 10.1002/jcc.20681 · DOI · Paper page
  6. 10.1093/bioinformatics/btq007 · DOI · Paper page
  7. 2019, Estimation of model accuracy in CASP13, Proteins: Structure, Function, and Bioinformatics, 87, 1361, 10.1002/prot.25767 · DOI · Paper page
  8. 10.1002/pro.2389 · DOI · Paper page
  9. Corder,G.W. and Foreman,D.I. (2009) Nonparametric Statistics for Non-Statisticians: A Step-By-Step Approach. Wiley. · DOI · Paper page
  10. 2019, Deep convolutional networks for quality assessment of protein folds, Bioinformatics, 34, 4046
  11. 2021, The trRosetta server for fast and accurate protein structure prediction, Nature protocols, 16, 5634, 10.1038/s41596-021-00628-9 · DOI · Paper page
  12. 10.1093/bioinformatics/bts565 · DOI · Paper page
  13. 10.1101/2021.10.02.462491 · DOI · Paper page
  14. 10.1073/pnas.89.22.10915 · DOI · Paper page
  15. 2019, Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13, Proteins: Structure, Function, and Bioinformaticsc, 87, 1165, 10.1002/prot.25697 · DOI · Paper page
  16. 10.1093/bioinformatics/btq003 · DOI · Paper page
  17. 2020, Improved Protein Model Quality Assessment By Integrating Sequential And Pairwise Features Using Deep Learning, Bioinformatics, 36, 5361
  18. 10.1093/bioinformatics/btu791 · DOI · Paper page
  19. 2018, High precision in protein contact prediction using fully convolutional neural networks and minimal sequence features, Bioinformatics, 34, 3308, 10.1093/bioinformatics/bty341 · DOI · Paper page
  20. 2021, CopulaNet: Learning residue co-evolution directly from multiple sequence alignment for protein structure prediction, Nature communications, 12, 1
  21. 1983, Dictionary of protein secondary structure: pattern recognition of hydroge-bonded and geometrical features, Biopolymers: Original Research on Biomolecules, 22, 2577, 10.1002/bip.360221211 · DOI · Paper page
  22. 2019, Prediction of interresidue contacts with DeepMetaPSICOV in CASP13, Proteins: Structure, Function, and Bioinformatics, 87, 1092, 10.1002/prot.25779 · DOI · Paper page
  23. 10.1371/journal.pone.0092197 · DOI · Paper page
  24. 2021, Assessment of protein model structure accuracy estimation in CASP14: Old and new challenges, Proteins: Structure, Function, and Bioinformatics, 89, 1940, 10.1002/prot.26192 · DOI · Paper page
  25. 2020, CGLFold: a contact-assisted de novo protein structure prediction using global exploration and loop perturbation sampling algorithm, Bioinformatics, 36, 2443, 10.1093/bioinformatics/btz943 · DOI · Paper page
  26. 2022, A de novo protein structure prediction by iterative partition sampling, topology adjustment, and residue-level distance deviation optimization, Bioinformatics, 38, 99
  27. 2020, AmoebaContact and GDFold as a pipeline for rapid de novo protein structure prediction, Nature Machine Intelligence, 2, 25, 10.1038/s42256-019-0130-4 · DOI
  28. 2021, ModFOLD8: accurate global and local quality estimates for 3D protein models, Nucleic acids research, 49, W425, 10.1093/nar/gkab321 · DOI · Paper page
  29. 2001, Generation and evaluation of dimension-reduced amino acid parameter representations by artificial neural networks, Molecular modeling annual, 7, 360, 10.1007/s008940100038 · DOI · Paper page
  30. 10.1093/nar/gkw1081 · DOI · Paper page
  31. 2021, Improving fragment-based ab initio protein structure assembly using low-accuracy contact-map predictions, Nature communications, 12, 1
  32. 2018, Critical assessment of methods of protein structure prediction (CASP)-Round XII, Proteins: Structure, Function, and Bioinformatics, 86, 7, 10.1002/prot.25415 · DOI · Paper page
  33. 2017, VoroMQA: Assessment of protein structure quality using interatomic contact areas, Proteins: Structure, Function, and Bioinformatics, 85, 1131, 10.1002/prot.25278 · DOI · Paper page
  34. 2019, Protein model quality assessment using 3D oriented convolutional neural networks, Bioinformatics, 35, 3313, 10.1093/bioinformatics/btz122 · DOI · Paper page
  35. 10.1016/S0076-6879(04)83004-0 · DOI · Paper page
  36. 2020, Improved protein structure prediction using potentials from deep learning, Nature, 577, 706, 10.1038/s41586-019-1923-7 · DOI · Paper page
  37. 2020, QDeep: distance-based protein model quality estimation by residue-level ensemble error classifications using stacked deep residual neural networks, Bioinformatics, 36, i285, 10.1093/bioinformatics/btaa455 · DOI · Paper page
  38. 10.1186/s12859-019-2669-9 · DOI · Paper page
  39. 2016, ProQ3: Improved model quality assessments using Rosetta energy terms, Scientific reports, 6, 1
  40. 10.1093/bioinformatics/btz828 · DOI · Paper page
  41. Su,H. et al. (2021) Improved Protein Structure Prediction Using a New Multi-Scale Network and Homologous Templates. Advanced Science, 2102592. · DOI · Paper page
  42. 2017, ProQ3D: improved model quality assessments using deep learning, Bioinformatics, 33, 1578, 10.1093/bioinformatics/btw819 · DOI · Paper page
  43. 10.1093/BIB/BBAA290 · DOI · Paper page
  44. 2018, Analysis of deep learning methods for blind protein contact prediction in CASP12, Proteins: Structure, Function, and Bioinformatics, 86, 67, 10.1002/prot.25377 · DOI · Paper page
  45. 2009, Evaluating the absolute quality of a single protein model using structural features and support vector machines, Proteins: Structure, Function, and Bioinformatics, 75, 638, 10.1002/prot.22275 · DOI · Paper page
  46. 2019, Assessment of protein model structure accuracy estimation in CASP13: challenges in the era of deep learning, Proteins: Structure, Function, and Bioinformatics, 87, 1351, 10.1002/prot.25804 · DOI · Paper page
  47. 2021, A Sequential Niche Multimodal Conformation Sampling Algorithm for Protein Structure Prediction, Bioinformatics, 37, 4357, 10.1093/bioinformatics/btab500 · DOI
  48. 2012, Ab initio protein structure assembly using continuous structure fragments and optimized knowledge-based force field, Proteins: Structure, Function, and Bioinformatics, 80, 1715, 10.1002/prot.24065 · DOI · Paper page
  49. 2021, Improved protein structure prediction by deep learning irrespective of co-evolution information, Nature Machine Intelligence, 3, 601, 10.1038/s42256-021-00348-5 · doi:10.1038/s42256-021-00348-5
  50. 10.1093/bioinformatics/btab632 · DOI
  51. 2021, MMpred: a distance-assisted multimodal conformation sampling for de novo protein structure prediction, Bioinformatics, 37, 4350, 10.1093/bioinformatics/btab484 · DOI · Paper page
  52. 2019, Deep-learning contact-map guided protein structure prediction in CASP13, Proteins: Structure, Function, and Bioinformatics, 87, 1149, 10.1002/prot.25792 · DOI · Paper page
  53. 2019, Underestimation-assisted global-local cooperative differential evolution and the application to protein structure prediction, IEEE Transactions on Evolutionary Computation, 24, 536
  54. 10.1073/pnas.1905068116 · DOI · Paper page
  55. Zhou,X.G. et al. (2020) Progressive and accurate assembly of multi-domain protein structures from cryo-EM density maps. bioRxiv, doi: https://doi.org/10.1101/2020.10.15.340455. · DOI

Cited by

See all 6

Metadata

Authors
Liu, J., He, G.-X., Zhao, K.-L., & Zhang, G.-J.
Venue
bioRxiv (Cold Spring Harbor Laboratory)
Publisher
openRxiv
Published
2022-01-12
OpenAlex
W4205750539
Cited by
6
References
18
Type
posted content
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.